From dd05add7b2b6004c5fa3a1f276f56d8668f86b65 Mon Sep 17 00:00:00 2001 From: Paulo Alcantara Date: Sat, 26 Sep 2026 19:20:30 -0300 Subject: netfs: zero the tail of a short DIO/unbuffered read The buffered read collector zero-fills the tail of a short read that stops below the inode's i_size (netfs_clear_unread()), so a read that races an extending write still returns the expected number of bytes. The non-buffered collector path does no such thing: it just records how much was transferred. Add the same zero-fill for the non-buffered case, gated on NETFS_SREQ_CLEAR_TAIL: a subreq's source sets that flag when a short result from it is known to be safe to treat as a hole, as opposed to NETFS_SREQ_HIT_EOF, which means the read genuinely ran off the end of the file and should be reported short as-is. Only CLEAR_TAIL should zero-fill here; a real EOF must stay a real short read. No source currently sets CLEAR_TAIL on an unbuffered/DIO subrequest, so this is inert on its own -- a following change teaches cifs to set it in the one case that needs it. Fixes: e2d46f2ec332 ("netfs: Change the read result collector to only use one work item") Reviewed-by: David Howells Reviewed-by: Namjae Jeon Signed-off-by: Paulo Alcantara Cc: Christian Brauner Cc: Matthew Wilcox Cc: Ronnie Sahlberg Cc: Shyam Prasad N Cc: Tom Talpey Cc: Bharath SM Cc: stable@vger.kernel.org --- fs/ext4/fast_commit.h | 189 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 189 insertions(+) create mode 100644 fs/ext4/fast_commit.h (limited to 'fs/ext4/fast_commit.h') diff --git a/fs/ext4/fast_commit.h b/fs/ext4/fast_commit.h new file mode 100644 index 000000000..2f77a37fb --- /dev/null +++ b/fs/ext4/fast_commit.h @@ -0,0 +1,189 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __FAST_COMMIT_H__ +#define __FAST_COMMIT_H__ + +/* + * Note this file is present in e2fsprogs/lib/ext2fs/fast_commit.h and + * linux/fs/ext4/fast_commit.h. These file should always be byte identical. + */ + +/* Fast commit tags */ +#define EXT4_FC_TAG_ADD_RANGE 0x0001 +#define EXT4_FC_TAG_DEL_RANGE 0x0002 +#define EXT4_FC_TAG_CREAT 0x0003 +#define EXT4_FC_TAG_LINK 0x0004 +#define EXT4_FC_TAG_UNLINK 0x0005 +#define EXT4_FC_TAG_INODE 0x0006 +#define EXT4_FC_TAG_PAD 0x0007 +#define EXT4_FC_TAG_TAIL 0x0008 +#define EXT4_FC_TAG_HEAD 0x0009 + +#define EXT4_FC_SUPPORTED_FEATURES 0x0 + +/* On disk fast commit tlv value structures */ + +/* Fast commit on disk tag length structure */ +struct ext4_fc_tl { + __le16 fc_tag; + __le16 fc_len; +}; + +/* Value structure for tag EXT4_FC_TAG_HEAD. */ +struct ext4_fc_head { + __le32 fc_features; + __le32 fc_tid; +}; + +/* Value structure for EXT4_FC_TAG_ADD_RANGE. */ +struct ext4_fc_add_range { + __le32 fc_ino; + __u8 fc_ex[12]; +}; + +/* Value structure for tag EXT4_FC_TAG_DEL_RANGE. */ +struct ext4_fc_del_range { + __le32 fc_ino; + __le32 fc_lblk; + __le32 fc_len; +}; + +/* + * This is the value structure for tags EXT4_FC_TAG_CREAT, EXT4_FC_TAG_LINK + * and EXT4_FC_TAG_UNLINK. + */ +struct ext4_fc_dentry_info { + __le32 fc_parent_ino; + __le32 fc_ino; + __u8 fc_dname[]; +}; + +/* Value structure for EXT4_FC_TAG_INODE. */ +struct ext4_fc_inode { + __le32 fc_ino; + __u8 fc_raw_inode[]; +}; + +/* Value structure for tag EXT4_FC_TAG_TAIL. */ +struct ext4_fc_tail { + __le32 fc_tid; + __le32 fc_crc; +}; + +/* Tag base length */ +#define EXT4_FC_TAG_BASE_LEN (sizeof(struct ext4_fc_tl)) + +/* + * Fast commit status codes + */ +enum { + EXT4_FC_STATUS_OK = 0, + EXT4_FC_STATUS_INELIGIBLE, + EXT4_FC_STATUS_SKIPPED, + EXT4_FC_STATUS_FAILED, +}; + +/* + * Fast commit ineligiblity reasons: + */ +enum { + EXT4_FC_REASON_XATTR = 0, + EXT4_FC_REASON_CROSS_RENAME, + EXT4_FC_REASON_JOURNAL_FLAG_CHANGE, + EXT4_FC_REASON_NOMEM, + EXT4_FC_REASON_SWAP_BOOT, + EXT4_FC_REASON_RESIZE, + EXT4_FC_REASON_RENAME_DIR, + EXT4_FC_REASON_FALLOC_RANGE, + EXT4_FC_REASON_INODE_JOURNAL_DATA, + EXT4_FC_REASON_ENCRYPTED_FILENAME, + EXT4_FC_REASON_MIGRATE, + EXT4_FC_REASON_VERITY, + EXT4_FC_REASON_MOVE_EXT, + EXT4_FC_REASON_MAX +}; + +#ifdef __KERNEL__ +/* + * In memory list of dentry updates that are performed on the file + * system used by fast commit code. + */ +struct ext4_fc_dentry_update { + int fcd_op; /* Type of update create / unlink / link */ + int fcd_parent; /* Parent inode number */ + int fcd_ino; /* Inode number */ + struct name_snapshot fcd_name; /* Dirent name */ + struct list_head fcd_list; + struct list_head fcd_dilist; +}; + +struct ext4_fc_stats { + unsigned int fc_ineligible_reason_count[EXT4_FC_REASON_MAX]; + unsigned long fc_num_commits; + unsigned long fc_ineligible_commits; + unsigned long fc_failed_commits; + unsigned long fc_skipped_commits; + unsigned long fc_numblks; + u64 s_fc_avg_commit_time; +}; + +#define EXT4_FC_REPLAY_REALLOC_INCREMENT 4 + +/* + * Physical block regions added to different inodes due to fast commit + * recovery. These are set during the SCAN phase. During the replay phase, + * our allocator excludes these from its allocation. This ensures that + * we don't accidentally allocating a block that is going to be used by + * another inode. + */ +struct ext4_fc_alloc_region { + ext4_lblk_t lblk; + ext4_fsblk_t pblk; + int ino, len; +}; + +/* + * Fast commit replay state. + */ +struct ext4_fc_replay_state { + int fc_replay_num_tags; + int fc_replay_expected_off; + int fc_current_pass; + int fc_cur_tag; + int fc_crc; + struct ext4_fc_alloc_region *fc_regions; + int fc_regions_size, fc_regions_used, fc_regions_valid; + int *fc_modified_inodes; + int fc_modified_inodes_used, fc_modified_inodes_size; +}; + +#define region_last(__region) (((__region)->lblk) + ((__region)->len) - 1) +#endif + +static inline const char *tag2str(__u16 tag) +{ + switch (tag) { + case EXT4_FC_TAG_LINK: + return "ADD_ENTRY"; + case EXT4_FC_TAG_UNLINK: + return "DEL_ENTRY"; + case EXT4_FC_TAG_ADD_RANGE: + return "ADD_RANGE"; + case EXT4_FC_TAG_CREAT: + return "CREAT_DENTRY"; + case EXT4_FC_TAG_DEL_RANGE: + return "DEL_RANGE"; + case EXT4_FC_TAG_INODE: + return "INODE"; + case EXT4_FC_TAG_PAD: + return "PAD"; + case EXT4_FC_TAG_TAIL: + return "TAIL"; + case EXT4_FC_TAG_HEAD: + return "HEAD"; + default: + return "ERROR"; + } +} + +#endif /* __FAST_COMMIT_H__ */ -- cgit v1.3.1